• 제목/요약/키워드: classification of posture

검색결과 108건 처리시간 0.024초

Development of Plantar Pressure Measurement System and Personal Classification Study based on Plantar Pressure Image

  • Ho, Jong Gab;Kim, Dae Gyeom;Kim, Young;Jang, Seung-wan;Min, Se Dong
    • KSII Transactions on Internet and Information Systems (TIIS)
    • /
    • 제15권11호
    • /
    • pp.3875-3891
    • /
    • 2021
  • In this study, a Velostat pressure sensor was manufactured to develop a plantar pressure measurement system and a C#-based application was developed to monitor and collect plantar pressure data in real time. In order to evaluate the characteristics of the proposed plantar pressure measurement system, the accuracy of plantar pressure index and personal classification was verified by comparing with MatScan, a commercial plantar pressure measurement system. As a result, the output characteristics according to the weight of the Velostat pressure sensor were evaluated and a trend line with the reliability of r2 = 0.98 was detected. The Root Mean Square Error(RMSE) of the weighted area was 11.315 cm2, the RMSE of the x coordinate of Center of Pressure(CoPx) was 1.036 cm and the RMSE of the y coordinate of Center of Pressure(CoPy) was 0.936 cm. Finally, inaccuracy of personal classification, the proposed system was 99.47% and MatScan was 96.86%. Based on the advantage of being simple to implement and capable of manufacturing at low cost, it is considered that it can be applied to various fields of measuring vital signs such as sitting posture and breathing in addition to the plantar pressure measurement system.

성인여성의 등면형상 유형화와 길 원형 설계 (Adult women's back type classification and Development of the Basic Bodice Pattern)

  • 최선윤;이정란
    • 한국의류학회지
    • /
    • 제27권7호
    • /
    • pp.758-769
    • /
    • 2003
  • In this research, I classified adult women's back types through anthropometric measurement and photographic measurement to present a judging individual body size according to the type. Also, Ⅰ calculated regression fomula by types and presented the basic bodice pattern. The results were as follows: 1. The result of factor analysis indicated that 5 factors were extracted and those factors comprised 75.89% of total variance. 2. According to the cluster analysis, Ⅰclassified the back types into 6 types. Type 1 was passive posture in the upper and the lower parts of the back. Type 2 was active posture in the upper and the lower parts of the back. Type 3 had the lowest protrusion of the back. Type 4 had the upper part of the back which is mostly bent downward. Type 5 was the most suitable shape. Type 6 had the lower part of the back which was turned over the most. 3. Ⅰconducted a discriminant analysis to judge the body types of individuals. 4. For the calculation of measurements necessary for the basic bodice pattern, Ⅰpresented regression formulas by each type. 5. By conducting the wearing experiments, Ⅰsuccessfully made the final basic bodice patterns by types. As a result of comparative experiments between the basic bodice patterns and comparison bodice pattern, the suitability of basic bodice patterns were more highly assessed.

유비쿼터스 헬스케어를 위한 활동상태 분류기 개발 (Development of the Activity Posture Classifier for Ubiquitous Health Care)

  • 김세진;정완영;정도운
    • 한국정보통신학회:학술대회논문집
    • /
    • 한국해양정보통신학회 2007년도 춘계종합학술대회
    • /
    • pp.703-706
    • /
    • 2007
  • 인체의 실시간 활동 모니터링은 활동량과 활동능력에 대한 중요한 정보를 제공한다. 본 연구에서 3축 가속도 센서와 무선센서노드를 활용하여 인체의 활동을 평가하고 응급상황을 인지할 수 있는 시스템을 개발하였다. 본 연구에 의해 구현된 실시간 시스템은 구현된 분류알고리즘을 통해 다양한 자세와 자세변화를 분류할 수 있으며, 추가적으로 낙상을 감지할 수 있다. 구현된 시스템의 성능평가 결과 높은 분류 정확성을 보였다.

  • PDF

Ergonomics Job Hazard Evaluation of Building Cleaners

  • Lee, Kyung-Sun;Lee, In-Seok;Kim, Hyun-Joo;Jung-Choi, KyungHee;Bahk, Jin-Wook;Jung, Myung-Chul
    • 대한인간공학회지
    • /
    • 제30권3호
    • /
    • pp.427-435
    • /
    • 2011
  • Objective: The objective of this study was to evaluate a work of building cleaners using the ergonomic methods. Background: Previous studies about cleaning worker describe typical physical demands of this work. They found that the most significant risk factors associated with the physical work of cleaners are static loads and repetitive movements and high output of force. Method: A head of ergonomics estimation was work analysis(define of combined task, work tool, work time and frequency of combined task) and posture analysis of worker. Results: The results showed that combined task of building cleaners was classification sweeping, mopping(wet), mopping(oil), moving barrels/carts, dumping trash bags, scrubbing, arrangement of cleaning tool, arrangement of circumferential, moving of cleaning tool, and waiting. The work time of combined task such as mopping(wet) and scrubbing indicated high ratio. The posture analysis of building cleaners indicated high value in bending of the head, lower arm, and hands. Conclusion: The findings appear to indicate that building cleaner were related to high risk of work-related musculoskeletal disorders. So, building cleaner would be required an interventional strategy, improvement of cleaning tools and working environment. Application: If ergonomics rule can be integrated into existing cleaning tools and work environments, the risk of occupational injuries will be reduced.

경직성 편마비 아동의 둔부 테이핑 적용이 선 자세에서 자세 및 균형에 미치는 영향 (The Effect of Gluteal Taping on Posture and Balance During Standing in Children with Hemiplegic Cerebral Palsy)

  • 서혜정;김중휘;손국경;전제규
    • 대한물리의학회지
    • /
    • 제9권4호
    • /
    • pp.391-398
    • /
    • 2014
  • PURPOSE: The purpose of the present study was to examine the effect of gluteal taping on posture and balance during standing in children with hemiplegic cerebral palsy (CP). METHODS: The subjects of this study were 13 children (six females, seven males; mean aged 8.5) with hemiplegic CP who were gross motor function classification system (GMFCS) level I. The change of posture and balance during standing before and after gluteal taping were measured using inclinometer, gross motor function measure, and functional reaching test. The collected data were analyzed using the paired t-test. RESULTS: The results of this study were as follows : 1) There were statistically significant decrease in the ant. tilt angle of pelvis after gluteal taping in children with hemiplegic CP (p<.05). 2) There were statistically significant increase in functional reaching test after gluteal taping (p<.05). 3) There was no statistically significant difference in gross motor function measure, but significant increase in one leg standing was observed (p<.05). CONCLUSION: As the above results, we suggest that gluteal taping could be effective on improving body alignment and dynamic balance ability during standing in children with hemiplegic CP. Further studies will be required for the short and long term effects of gluteal taping on improving postural symmetry and balance.

Classification of Upper Body Somatotypes according to the Age Group : Using 3D-Body Scan Data

  • Na, Hyun-Shin
    • International Journal of Costume and Fashion
    • /
    • 제5권1호
    • /
    • pp.1-13
    • /
    • 2005
  • Two hundreds of female aged 19 years old and up were recruited to evaluate the postural changes and bilateral variation of asymmetry over age. To find out the differences among the age group, subjects were classified into 5 groups, early young age(19-29), late young age(30-39), early middle age(40-49), late middle age(50-59), and old age(60-). 35 body measurements were taken by the 3-D body scanner which allowed us to take measurements which cannot be measured using traditional methods, including the shape of a cross section, slice area surface are, and volume. Bilateral variations were observed as a function of age; Depth of scapular point level, scapular point to center back, and blade angle. Postural change of anterior cervical angle, upper anterior thoracic angle, upper posterior thoracic angle, posterior cervical angle, and center back/center front ratio were also exhibited. In each measurements, subjects were classified into normal, and abnormal group. Percentiles of abnormal in shoulder line angle, blade angle, neck point $\∼$ acromial point $\∼$ scapular point, posterior cervical angle, and upper posterior thoracic angle were increased over age group. The upper body of lateral view was classified into 3 types of posture based on the previous research; straight, erect(leaning back), and stooped(bent forward). The percentiles of subjects who have straight postures were decreased as a function of age, but those of stooped postures were increased. Subjects who have erect postures did not so. The stooped posture group shows the big cervical fossa angle, anterior cervical angle, posterior cervical angle, upper posterior thoracic angle, and the small upper anterior thoracic angle comparing to the straight and erect posture group. These results could be apply for clothing construction reflecting the changes in back, shoulder, neck, and the bilateral asymmetry according to the target age group.

인체 정보 재구성을 통한 3D캐릭터 모델링 (3D Character Modeling Through Reconstruction of Human Body Information)

  • 곽현민;김관웅;조해성;김남희;채균식;박찬종;이상태
    • 대한전자공학회:학술대회논문집
    • /
    • 대한전자공학회 2003년도 하계종합학술대회 논문집 V
    • /
    • pp.2693-2696
    • /
    • 2003
  • 우리나라의 국민표준체위조사는 1979년 1차 조사를 시작으로 약 5-6년 주기로 실시되고 있으며, 1997년 제 4차 조사가 실시되었다. 국민체위조사 결과를 기반으로 의류, 신발, 가구 등 관련산업의 제품설계에 반영되었다. 본 논문에서는 국민표준체위조사 결과 자료를 기본으로 성별, 연령별, 체형별로 사용자를 분류한 후 체형별 분류를 위한 인체 측정치를 도출하였다. 도출된 인체측정치의 상관관계 분석, 대표적인 항목 도출 등의 과정을 통하여 3D 캐릭터를 구성하였다. 구성을 위한 과정으로 골프, 테니스 등의 스포츠 동작을 효율적으로 나타낼 수 있는 인체 측정치를 도출하였다. 항목이 결정되면 각 타입의 3D 캐릭터를 구성 할 수 있는 치수를 제시하여 생성하였다. 스포츠의 자세 및 동작분석에 대한 이론적 접근에서 가시적인 정보제공 및 자세·동작분석 프로토콜을 개발함으로서 자세 및 동작에 대한 정량적, 객관적 평가가 가능해졌다.

  • PDF

고령사회를 대비한 뉴 시니어 여성의 체간부 체형 분석 (Torso shape analysis of new senior women for the aged society)

  • 어미경;김아영
    • 한국의상디자인학회지
    • /
    • 제21권2호
    • /
    • pp.95-108
    • /
    • 2019
  • This study aims to determine the characteristics of new senior women's torso shapes. The data was collected from the 7th Size Korea, which analyzed 412 women between the ages of 55-69. A factor analysis was performed based on 20 indices, including eight based on circumference, eight based on height and length measurements, and four based on torso flattening. The results of the factor analysis suggest five main factors: torso silhouette, longitudinal size of the body, torso flattening rate, abdominal shape, and posterior longitudinal size. The results of the cluster analysis suggest three overall types: Type 1 is the inverted triangular obese shape which is characterized by large breasts, small buttocks, a short height, and a forward-bending posture; Type 2 is the rectangular, slim shape which is characterized by a forward neck and a flat front and back of the torso, and is the most slender among the three types; Type 3 is the large rectangular, overall obese shape, which is characterized by a round shape with large breasts, waist, and buttocks, and a forward-bending posture with a protruding back, and this is the most obese type. According to the results of the cross-tabulation, women aged 55-59 showed no trend in body shape; women aged 60-64 showed an increases in the inverted triangular obese shape and the large rectangular, overall obese shape; women aged 65-69 showed an increase in the large rectangular, overall obese shape and a decrease in the rectangular slim shape. In summary, new senior women showed body shape characteristics of being short, more obese having, a bent over posture. As they grew older, the curves disappeared, and the body becomes rounder. The study found that variation in body shape exists among new senior women in the aged society.

딥러닝 기반 운동 자세 교정 시스템의 성능 (Performance of Exercise Posture Correction System Based on Deep Learning)

  • 황병선;김정호;이예람;경찬욱;선준호;선영규;김진영
    • 한국인터넷방송통신학회논문지
    • /
    • 제22권5호
    • /
    • pp.177-183
    • /
    • 2022
  • 최근 COVID-19로 인해 홈 트레이닝의 관심도가 증가하고 있다. 이에 따라 HAR(human activity recognition) 기술을 홈 트레이닝에 적용한 연구가 진행되고 있다. 기존 HAR 분야의 논문에서는 동적인 자세보다는 앉기, 일어서기와 같은 정적인 자세들을 분석한다. 본 논문은 동적인 운동 자세를 분석하여 사용자의 운동 자세 정확도를 보여주는 딥러닝 모델을 제안한다. AI hub의 피트니스 이미지를 blaze pose를 사용하여 사람의 자세 데이터를 분석한다. 3개의 딥러닝 모델: RNN(recurrnet neural networks), LSTM(long short-term memory networks), CNN(convolution neural networks)에 대하여 실험을 진행한다. RNN, LSTM, CNN 모델의 f1-score는 각각 0.49, 0.87, 0.98로 CNN 모델이 가장 적합하다는 것을 확인하였다. 이후 연구로는, 다양한 학습 데이터를 사용하여 더 많은 운동 자세를 분석할 예정이다.

인체정보 DB의 경제적인 조합을 통한 골프 스윙 동작 분석용 3D 캐릭터 모델링 (The 3D Character Modeling for Golf Swing Motion Analysis by Economical Verification of Body Information)

  • 곽현민;채균식;박찬종;이상태
    • 감성과학
    • /
    • 제6권2호
    • /
    • pp.59-64
    • /
    • 2003
  • 우리나라의 국민표준체위조사는 1979년 1차 조사를 시작으로 약 5∼6년 주기로 실시되고 있으며, 1997년 제4차 조사가 실시되었다. 국민표준체위조사 결과를 기반으로 한 인체측정치는 의류, 신발, 가구 등 관련산업의 제품설계에 반영되었다. 본 논문에서는 국민표준체위조사 결과자료를 기본으로 성별, 연령별, 체형별로 사용자를 분류한 후 체형별 분류를 위한 인체측정치를 도출하였다 도출된 인체측정치의 상관관계를 분석, 대표적인 항목 도출 등의 과정을 통하여 3D 캐릭터를 구성하였다. 구성을 위한 과정으로 골프, 테니스 등의 스포츠 동작을 효율적으로 나타낼 수 있는 인체 측정치를 도출하였다. 항목이 결정되면 각 타입의 3D 캐릭터를 구성할 수 있는 치수를 제시하여 생성하였다. 스포츠의 자세 및 동작분석에 대한 이론적 접근에서 가시적인 정보제공 및 자세ㆍ동작분석 프로토콜을 개발함으로써 자세 및 동작에 대한 정량적ㆍ객관적 평가가 가능해졌다.

  • PDF